A Survey on Human Activity Recognition using Sensors and Deep Learning Methods

摘要

One of the most difficult challenges in the field of computer vision is human activity recognition (HAR). The main purpose of intelligent video system is to determine the actions and activities of the individual. This action monitoring system can be used in a variety of settings, which include human-computer interaction, tracking, security, and health monitoring. Detecting activity in an uncircumscribed territory remains a challenging task with multiple challenges, despite ongoing efforts in this area. Throughout this article, some recent research papers that include different approaches are analyzed to detect different human activities. Wearable devices and phone sensors are required for this task. The vision-based approach has become a prevalent HAR technique, according to the researchers.